Content
The dataset provides the total extent for each day for the entire time period (1978-2015). There are seven variables:
- Year
- Month
- Day
- Extent: unit is 10^6 sq km
- Missing: unit is 10^6 sq km
- Source: Source data product web site: http://nsidc.org/data/nsidc-0051.html
- Hemisphere: North or South
The main problem with this dataset it that measures are taken every 2 days, while the co2 are monthly.
## Year Month Day Extent
## Min. :1978 Min. : 1.000 Min. : 1.00 Min. : 2.080
## 1st Qu.:1992 1st Qu.: 4.000 1st Qu.: 8.00 1st Qu.: 7.601
## Median :2001 Median : 7.000 Median :16.00 Median :12.217
## Mean :2001 Mean : 6.507 Mean :15.74 Mean :11.495
## 3rd Qu.:2010 3rd Qu.:10.000 3rd Qu.:23.00 3rd Qu.:15.114
## Max. :2019 Max. :12.000 Max. :31.00 Max. :20.201
##
## Missing
## Min. :0.000e+00
## 1st Qu.:0.000e+00
## Median :0.000e+00
## Mean :3.074e-06
## 3rd Qu.:0.000e+00
## Max. :2.400e-02
##
## Source.Data
## ['ftp://sidads.colorado.edu/pub/DATASETS/nsidc0051_gsfc_nasateam_seaice/final-gsfc/north/daily/1978/nt_19781026_n07_v1.1_n.bin']: 1
## ['ftp://sidads.colorado.edu/pub/DATASETS/nsidc0051_gsfc_nasateam_seaice/final-gsfc/north/daily/1978/nt_19781028_n07_v1.1_n.bin']: 1
## ['ftp://sidads.colorado.edu/pub/DATASETS/nsidc0051_gsfc_nasateam_seaice/final-gsfc/north/daily/1978/nt_19781030_n07_v1.1_n.bin']: 1
## ['ftp://sidads.colorado.edu/pub/DATASETS/nsidc0051_gsfc_nasateam_seaice/final-gsfc/north/daily/1978/nt_19781101_n07_v1.1_n.bin']: 1
## ['ftp://sidads.colorado.edu/pub/DATASETS/nsidc0051_gsfc_nasateam_seaice/final-gsfc/north/daily/1978/nt_19781103_n07_v1.1_n.bin']: 1
## ['ftp://sidads.colorado.edu/pub/DATASETS/nsidc0051_gsfc_nasateam_seaice/final-gsfc/north/daily/1978/nt_19781105_n07_v1.1_n.bin']: 1
## (Other) :26348
## hemisphere
## north:13177
## south:13177
##
##
##
##
##
For this reason, we had to: - Take a look at the possible exising cycles of ice extent during each month - See if we can compress all that information in a few features (like mean and variance or jitter or some statistical feature).
## Analysis of Variance Table
##
## Response: Extent
## Df Sum Sq Mean Sq F value Pr(>F)
## Date 1 1965 1965 102.7799 < 2.2e-16 ***
## Year 1 31833 31833 1665.3461 < 2.2e-16 ***
## Month 1 296 296 15.5032 8.258e-05 ***
## Day 1 1713 1713 89.5968 < 2.2e-16 ***
## Missing 1 2 2 0.1213 0.7277
## hemisphere 1 461 461 24.1423 9.001e-07 ***
## `Global Extent` 1 20617 20617 1078.5827 < 2.2e-16 ***
## `North-South Difference` 1 0 0 0.0000 0.9984
## Residuals 26345 503590 19
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Thankfully, we saw almost no variation within the days, as was seen on IceSurface.R, the ice extent remains almost constant for each day of the month. This is reasonable, since it has no sense having a sensible decrease in ice extent in a certain days, since it is a rather long-termed effect.
## Don't know how to automatically pick scale for object of type table. Defaulting to continuous.